CN108334353A - Skill development system and method - Google Patents
Skill development system and method Download PDFInfo
- Publication number
- CN108334353A CN108334353A CN201710774596.4A CN201710774596A CN108334353A CN 108334353 A CN108334353 A CN 108334353A CN 201710774596 A CN201710774596 A CN 201710774596A CN 108334353 A CN108334353 A CN 108334353A
- Authority
- CN
- China
- Prior art keywords
- technical ability
- skill
- elements
- store
- skill elements
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/35—Creation or generation of source code model driven
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/36—Software reuse
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of skill development system and method, which includes:Skill development platform and technical ability store;The technical ability used for application developer and skill elements are stored in technical ability store;The skill development platform includes:Preprocessing module, the use feature vector for determining each skill elements in technical ability store, the skill elements include:The semantic slot that the intention of technical ability, the saying template being each intended to encompass, each saying template include;Receiving module, the attributive character of the technical ability to be developed for receiving skill development person's upload;Recommendation process module, for according in technical ability store each skill elements using feature vector and the attributive character of the technical ability to be developed, determine skill elements to be recommended;Push unit, for the skill elements to be recommended to be recommended the skill development person, so that skill development person selection meets the skill elements Develop ability of application demand.Using the present invention, can sharpen one's skills development efficiency.
Description
Technical field
The present invention relates to natural language processing fields, and in particular to a kind of skill development system and platform.
Background technology
With the development of mobile intelligent terminal and information network technique, people are handed in more and more scenes using voice
Mutually application, such as using intelligent sound box as entrance, interactive voice uses weather/stock/music/traffic/alarm clock/prompting etc.
Using each application includes one or more technical ability.In another example using vehicle-mounted vehicle device as entrance, interactive voice using LBS/ navigation/
The applications such as radio station/music or technical ability.Thus, also there are more and more dialog mode artificial intelligence open platforms, such as hundred in industry
The DuerOS of degree, the Alexa etc. of Amazon, providing one for application developer or skill development person can be with development and application or technical ability
System.Meanwhile a kind of purpose of abundant ecology that sharing win-win each other is built for open platform, it is also typically provided technical ability quotient
The market of this similar type in city so that the technical ability of developer's exploitation can be published in store, both can be directly for terminal
Family selection uses, and can also be chosen in application for third party application developer, terminal user is available to by terminal applies
It uses.
Or existing shared skill is developed by skill development person oneself or be based on completely to the technical ability in existing technical ability store
Oneself application demand can be combined to carry out secondary development, such as increase new intention or existing intentional saying template for new technical ability.
For example, skill development person looks on the bright side of things, one technical ability listened to music of hair, the technical ability can not only listen to music, and can also carry out music point
It enjoys, music query etc.;Skill development person finds a technical ability music walkman for supporting similar intention in technical ability store, still
This technical ability can only listen to music, can not carry out music share, music query;Skill development person needs on the basis of this technical ability
It carries out music and shares the exploitation with music query.
No matter which kind of above-mentioned developing method for technical ability, be required for putting into more time or larger energy by skill development person, such as
Increase new saying template, develops the technical ability for being suitble to oneself application demand;If skill development person needs to newly increase a meaning
Figure, in order to ensure to be intended to the comprehensive of covering saying, then it is newly to be intended to increase more comprehensively to need to take more time with energy
Saying template, such as skill development person needs to increase by one and is intended to " send snatch of music to friend ", in order to ensure to be intended to cover
Lid saying it is comprehensive, which, which usually requires to increase many saying templates, such as " is sent to this section of music
{ friend } " " this section is issued { friend } and heard " " hearing this section of song to { friend } " etc., wherein { friend } is
Semantic slot in saying template, therefore, the process for increasing saying template are cumbersome;Further, since many skill development persons lack
Natural language processing professional knowledge, it is difficult to which accurate comprehensively covering is current to be intended to saying template.
Invention content
The embodiment of the present invention provides a kind of skill development system and method, is worked skill development with reducing skill development person
Complexity, and improve development efficiency.
For this purpose, the present invention provides the following technical solutions:
A kind of skill development system, including:Skill development platform and technical ability store;Shared technical ability is stored in technical ability store
And skill elements, the skill elements include:The intention of technical ability, the saying template being each intended to encompass, each saying template packet
The semantic slot contained;
The skill development platform includes:
Preprocessing module, the use feature vector for determining each skill elements in technical ability store, the skill elements packet
It includes:The semantic slot that the intention of technical ability, the saying template being each intended to encompass, each saying template include;
Receiving module, the attributive character of the technical ability to be developed for receiving skill development person's upload;
Recommendation process module is used for the use feature vector according to each skill elements in technical ability store and the skill to be developed
The attributive character of energy, determines skill elements to be recommended;
Push unit, for the skill elements to be recommended to be recommended the skill development person, so that the technical ability
Developer selects the skill elements Develop ability for meeting application demand.
Preferably, the preprocessing module includes:
Taxon for being divided in advance according to vertical field to the technical ability in technical ability store, and obtains technical ability
Vertical field class label;
First computing unit, for according to skilled vertical field class label in technical ability store, calculating each technical ability
Attribute feature vector;
Second computing unit, for according to the attribute feature vector of each technical ability, each skill elements in numeracy skills store
Use feature vector.
Preferably, the attribute feature vector includes:The semanteme of vertical field class label feature, technical ability belonging to technical ability
Understand term vector feature, the online number of request of technical ability, the user's evaluation score of technical ability that part generates.
Preferably, second computing unit is additionally operable in technical ability store skilled attribute feature vector update
Afterwards, the use feature vector of each skill elements in technical ability store is recalculated.
Preferably, the recommendation process module includes:
Metrics calculation unit, for after the attributive character that the receiving module receives the technical ability to be developed, successively
The distance between the attributive character using feature vector and the technical ability to be developed of each skill elements in numeracy skills store;
Selecting unit is less than the skill elements of given threshold as skill elements to be recommended for chosen distance;Or
The skill elements of the ascending forward setting number that sorts of chosen distance are as skill elements to be recommended.
Preferably, the receiving module is additionally operable to receive the technical ability that skill development person uploads, and the technical ability is published to
The technical ability store.
A kind of developing method for technical ability, the method includes:
Determine the attributive character of technical ability to be developed;
The attributive character of the technical ability to be developed is uploaded to skill development platform;
The skill elements that skill development platform is recommended are obtained, the skill elements include:The intention of technical ability, each intention packet
The semantic slot that saying template, each saying template contained includes;
Selection meets the skill elements of application demand;
Utilize the skill elements Develop ability of selection.
Preferably, the method further includes:
Skill development platform predefines the use feature vector of each skill elements in technical ability store;
Skill development platform is after the attributive character for receiving the technical ability to be developed, each skill in numeracy skills store successively
The distance between the attributive character using feature vector and the technical ability to be developed of energy element;
The skill elements that chosen distance is less than given threshold are recommended;Or the ascending sequence of chosen distance is forward
The skill elements of setting number are recommended.
Preferably, the skill development platform predefines the use feature vector packet of each skill elements in technical ability store
It includes:
The skill development platform in advance divides the technical ability in technical ability store according to vertical field, and obtains technical ability
Vertical field class label;
According to skilled vertical field class label in technical ability store, the attribute feature vector of each technical ability is calculated;
According to the attribute feature vector of each technical ability, the use feature vector of each skill elements in numeracy skills store.
Preferably, the use feature vector of each skill elements is also wrapped in the predetermined technical ability store of the skill development platform
It includes:
In technical ability store after skilled attribute feature vector update, the skill development platform recalculates technical ability
The use feature vector of each skill elements in store.
Preferably, the attribute feature vector includes:The semanteme of vertical field class label feature, technical ability belonging to technical ability
Understand term vector feature, the online number of request of technical ability, the user's evaluation score of technical ability that part generates.
Preferably, the description file of skill elements includes the intended scope and saying example of skill elements;The selector
Close application demand skill elements include:
Meet the skill elements of application demand according to the selection of the description file of the skill elements.
Preferably, described to include using the skill elements Develop ability of selection:
The description file for editing technical ability to be developed, the skill elements of selection are added in technical ability to be developed.
Preferably, described to include using the skill elements Develop ability of selection:
The skill elements of selection are customized, the skill elements customized;
The description file for editing technical ability to be developed, the skill elements of customization are added in technical ability to be developed.
Preferably, the method further includes:
If the skill elements that skill development platform is recommended do not meet the skill elements of application demand, by browsing skill
The description file selection of other skill elements meets the skill elements of application demand in energy store, or is met by retrieving selection
The skill elements of application demand.
Preferably, the method further includes:
The technical ability that exploitation is completed is published in the technical ability store.
Skill development system and method provided in an embodiment of the present invention utilizes the shared skill elements issued in technical ability store
And shared technical ability recommends corresponding skill elements, skill development person in skill development person's Develop ability from trend skill development person
Can be selected meet the skill elements of application demand according to the description file of skill elements, then utilize the skill elements of selection into
Row skill development, thus greatly reduces the complexity of skill development work, and improves development efficiency.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only one described in the present invention
A little embodiments, for those of ordinary skill in the art, other drawings may also be obtained based on these drawings.
Fig. 1 is the block diagram of skill development system of the embodiment of the present invention;
Fig. 2 is the structural schematic diagram of preprocessing module in skill development system of the embodiment of the present invention;
Fig. 3 is the flow chart of developing method for technical ability of the embodiment of the present invention;
Fig. 4 is the flow chart using feature vector that skill development platform determines each skill elements in the embodiment of the present invention.
Specific implementation mode
In order to make those skilled in the art more fully understand the scheme of the embodiment of the present invention, below in conjunction with the accompanying drawings and implement
Mode is described in further detail the embodiment of the present invention.
For shared technical ability is utilized in the prior art, simultaneously connected applications demand carries out the complicated, effect that works existing for secondary development
The low problem of rate, the embodiment of the present invention provide a kind of skill development system and method, and skill development platform utilizes in technical ability store
The attribute of existing shared skill elements, the technical ability to be developed provided when developing new technical ability according to skill development person holds sign vector,
Corresponding skill elements, skill development person are recommended therefrom the skill elements for meeting application demand to be selected to open from trend skill development person
Send out technical ability.
Element to be used is needed when the skill elements refer to Develop ability, specifically includes the intention of technical ability, each intention
Saying template, each saying template semantic slot.
Skill elements developer is different from skill development person, and the absorbed point of skill elements developer is where skill elements
The coverage and application effect of skill elements, skill elements developer generally have higher natural language processing in vertical field
Ability;And the absorbed point of skill development person is the business demand and dialog logic demand of current technical ability, when Develop ability, uses
Skill elements only need meet the needs of current technical ability, the skill elements used are one in vertical field where it
Fraction, coverage is not comprehensive enough, and skill development person does not require natural language processing ability.
When the skill elements that exploitation is completed are published to technical ability store by skill elements developer, need to provide current technical ability member
The intended scope and saying example of element, are checked, the intended scope of the skill elements when for skill development person using skill elements
It can be stored in the description file of skill elements with saying example, the description file format is " being intended to name saying example ",
It the following is intended scope and the exemplary example of saying in description file:
HKUST News are gone in navigation navigation
How to get to navigation goes HKUST News
Locate I where
Locate I now where
Wherein, navigation is navigation purposes, and locate is intended to for position enquiring, then the intention model of current skill elements
It encloses comprising two intentions, i.e. navigation purposes and position enquiring are intended to.
As shown in Figure 1, being the block diagram of skill development system of the embodiment of the present invention.
In this embodiment, the system comprises:Skill development platform 11 and technical ability store 12;It is stored in technical ability store 12
There are shared technical ability and the skill elements, the skill elements to include:It is the intention of technical ability, the saying template being each intended to encompass, each
The semantic slot that saying template includes.The skill development platform 11 includes following module:
Preprocessing module 111, the use feature vector for determining each skill elements in technical ability store;
Receiving module 112, the attributive character of the technical ability to be developed for receiving skill development person's upload;
Recommendation process module 113, for according to the use feature vectors of each skill elements in technical ability store and described waiting out
The attributive character for sending out technical ability, determines skill elements to be recommended;
Push unit 114, for the skill elements to be recommended to be recommended the skill development person, so that the skill
Energy developer's selection meets the skill elements Develop ability of application demand.For example, showing these skill elements to skill development person
Title, chained address etc..
It should be noted that in practical applications, the technical ability store 12 can be used as an independent part, can also collect
At on the skill development platform 11, this embodiment of the present invention is not limited.
Fig. 2 shows a kind of structural schematic diagrams of preprocessing module in skill development system of the embodiment of the present invention.
The preprocessing module 111 includes:
Taxon 21 for being divided in advance according to vertical field to the technical ability in technical ability store, and obtains technical ability
Vertical field class label.
First computing unit 22, for according to skilled vertical field class label in technical ability store, calculating each skill
The attribute feature vector of energy;
Second computing unit 23, for according to the attribute feature vector of each technical ability, each skill elements in numeracy skills store
Use feature vector.
Above-mentioned taxon 21 specifically can set initial classes first, in accordance with industry to the division in the vertical field of current technical ability
Then distinguishing label supplements the initial category label in conjunction with the skill collection in technical ability store, obtains technical ability store
The vertical field class label of middle technical ability.The class label that the vertical field of technical ability in current technical ability store is divided as industry
For " music, video, game, social activity, trip, shopping ", above-mentioned division classification is carried out according to the skill collection in technical ability store
Supplement, obtains vertical field class label " music, video, game, social activity, trip, shopping, novel, robot, take-away ".Into
One step, taxon 21 can also update the initial category label into Mobile state, for example can be that timing updates or determines
Phase updates.For example, determine a update cycle, it is within each update cycle that the very fast or more label of technical ability incrementss is automatic
It is added in initial category label, the less label of technical ability incrementss is deleted from initial category label.
In embodiments of the present invention, the attribute feature vector of technical ability includes that the vertical field class label belonging to technical ability is special
Term vector feature, the online number of request of technical ability, the user's evaluation score of technical ability of the semantic understanding part generation of sign, technical ability.Its
In:
Hanging down belonging to the dimension of the vertical field class label feature belonging to the technical ability is skilled in technical ability store
Straight field total number of labels, as in technical ability store institute it is skilled belonging to vertical field total number of labels be 50, then the technical ability institute
The dimension of the vertical field class label feature belonged to is 50, wherein vertical field class label feature belonging to current technical ability
Value is 1, and the value of other vertical field class label features is 0.
The term vector feature that the semantic understanding part of the technical ability generates, the i.e. term vector of the saying template generation of technical ability,
It is generated after being segmented by the saying template to current technical ability, the prior art may be used in specific generation method, such as utilizes and says
The inverse document frequency of method template generates corresponding term vector.
The dimension for the term vector feature that the semantic understanding part of technical ability generates skilled semantic reason in technical ability store
The term vector sum that solution part generates, as the sum of the term vector of technical ability store institute skilled semantic understanding part generation is
7000, then the dimension for the term vector feature that the semantic understanding part of technical ability generates is 7000, belongs to the semantic reason of current technical ability
The term vector feature value that solution part generates is 1, and other term vector feature values are 0.
The online number of request of technical ability and the user's evaluation score of technical ability can be counted to obtain by skill development platform.
The size of the attribute feature vector of technical ability in technical ability store it is skilled belonging to vertical field class label number+
Technical ability store skilled semantic understanding part generate the sum+1+1 of term vector, as in technical ability store institute it is skilled it is affiliated
Vertical field number of tags is 50, and the sum for the term vector that the skilled semantic understanding part of institute generates is 7000, then technical ability
Attribute feature vector size be 50+7000+1+1=7052 dimension.
The use feature vector of the skill elements indicates that current skill elements in skill development, recommend corresponding technical ability
When, the case where technical ability uses and current skill elements are not used.
The skill elements using feature vector can use skill elements recommend the attributive character of corresponding technical ability to
Amount is calculated, such as the use feature vector of current skill elements uCircular such as formula (1) shown in:
Wherein,Indicate that the attribute feature vector of technical ability j is made when current skill elements u recommends technical ability j by technical ability j
With;Indicate that the attribute feature vector of technical ability k is not used by technical ability k when current skill elements u recommends technical ability k;IrAnd Inr
When indicating that current skill elements u recommends technical ability, the technical ability of the skill collection and unused skill elements u of skill elements u is used
Set, β and γ indicate the weight that current skill elements are used and are not used by respectively, specifically can be according to application demand or reality
Test result determination.
It should be noted that due to the online number of request of each technical ability in technical ability store, the user's evaluation of technical ability must grade is
Dynamic change, i.e., the update of the maintenance of technical ability, the vertical field class label of technical ability, technical ability are made according to skill development person
With information such as situations, the first computing unit 22 needs to calculate the attributive character for updating each technical ability, correspondingly, in technical ability store
After skilled attribute feature vector update, the second computing unit 23 also needs to recalculate each skill elements in technical ability store
Use feature vector.
In embodiments of the present invention, the attributive character of the technical ability to be developed includes:The vertical field class label of technical ability,
Term vector feature, the online number of request of technical ability, the user's evaluation score of technical ability of the semantic understanding part generation of technical ability.It needs
It is bright, since current technical ability to be developed is not published in technical ability store also, so the semantic understanding part in its attributive character
The term vector of generation, the online number of request of technical ability, the user's evaluation score of technical ability is sky, to obtain current Develop ability
Attributive character.
Correspondingly, the recommendation process module 113 in Fig. 1 can be based on each technical ability member in the above-mentioned technical ability store being calculated
Use the feature vector of element, each skill elements use feature vector and the technical ability to be developed in numeracy skills store successively
The distance between attributive character determines skill elements to be recommended according to calculated distance.The skill elements include:
The semantic slot that the intention of technical ability, the saying template being each intended to encompass, each saying template include.
A kind of concrete structure of recommendation process module 113 may include following each unit:
Metrics calculation unit, for after the attributive character that receiving module 112 receives technical ability to be developed, calculating skill successively
The distance between the attributive character using feature vector and the technical ability to be developed of each skill elements in energy store 12;
Selecting unit is less than the skill elements of given threshold as skill elements to be recommended for chosen distance;Or
The skill elements of the ascending forward setting number that sorts of chosen distance are as skill elements to be recommended.
Skill development system provided in an embodiment of the present invention, skill development platform utilize the shared skill issued in technical ability store
Energy element and shared technical ability are opened when receiving the attributive character of technical ability to be developed of skill development person's upload from trend technical ability
Originator recommends corresponding skill elements, so that skill development person is therefrom selected the skill elements for meeting application demand, then utilizes
The skill elements of selection carry out skill development reduces the complexity of skill development to substantially increase the efficiency of skill development
Degree.
Certainly, skill development person can also utilize the skill development platform 11 in Fig. 1, and the technical ability that exploitation is completed is published to
Technical ability store is used for other skill development persons.For example, receiving skill development by the receiving module 112 in skill development platform
The technical ability that person uploads, and the technical ability is published in technical ability store 12.Certainly, in practical applications, can also be in the present invention
Independent technical ability publication engine (not shown) is set in system, and skill development person issues the skill that engine completes exploitation by the technical ability
It can be published in technical ability store 12.
Correspondingly, the embodiment of the present invention also provides a kind of developing method for technical ability, as shown in figure 3, being skill of the embodiment of the present invention
The flow chart of energy development approach, includes the following steps:
Step 301, the attributive character of technical ability to be developed is determined.
The attributive character of the technical ability to be developed includes:The vertical field class label of technical ability, the semantic understanding portion of technical ability
It is mitogenetic at term vector feature, the online number of request of technical ability, the user's evaluation score of technical ability.
Specifically, skill development person can determine current according to the vertical field class label of technical ability in current technical ability store
The vertical field class label of Develop ability.In addition, since current technical ability to be developed is not published in technical ability store also, so its
The online number of request of term vector, technical ability that semantic understanding part in attributive character generates, the user's evaluation score of technical ability are
Sky, to obtain the attributive character of current Develop ability.
Step 302, the attributive character of the technical ability to be developed is uploaded to skill development platform.
Step 303, the skill elements that skill development platform is recommended are obtained, the skill elements include:It is the intention of technical ability, every
The semantic slot that a saying template being intended to encompass, each saying template include.
It should be noted that in embodiments of the present invention, skill development platform needs to predefine each skill in technical ability store
The use feature vector of energy element.Correspondingly, after receiving the attributive character of technical ability to be developed of skill development person's upload, root
Determine skill elements to be recommended according to the attributive character using feature vector and technical ability to be developed of each skill elements, and by these
Skill elements recommend the skill development person, for example, showing title, the chained address of these skill elements to skill development person
Deng.Skill development platform determines that the detailed process of skill elements to be recommended will be described in detail later.
Step 304, the skill elements of application demand are met according to the selection of the description file of the skill elements.
The description file of the skill elements includes the intended scope and saying example of skill elements.
The intended scope and saying for the skill elements and skill elements that skill development person recommends according to skill development platform are shown
Example, the skill elements that selection meets application demand develop corresponding technical ability.
Step 305, the skill elements Develop ability of selection is utilized.
Specifically, skill development person can be added the skill elements of selection by the description file of editor's technical ability to be developed
Enter into current technical ability.
It should be noted that if the skill elements that skill development platform is recommended cannot fully meet application demand, technical ability
Developer can also be selected by browsing the description file of other skill elements in technical ability store, or be intended to by saying
It retrieves to retrieve the intention or skill elements that meet belonging to the saying template of application demand, selects corresponding skill elements.Certainly, such as
Do not found in fruit technical ability store meet application demand skill elements can also oneself exploitation.
Below by taking skill development person develops the technical ability of " social music " as an example, illustrate the mistake of skill development person's Develop ability
Journey.
Assuming that the technical ability intention of " social music " divides three types, the first kind to be music queries, the second class is friend's requesting song,
Third class is that certain section of music is sent to friend to allow its game of guessing the titles of songs name.The first kind is intended to the technical ability member recommended by skill development platform
MusicSearch in plain A.music is intended to obtain;Second class is intended to skill development person by browsing technical ability member in technical ability store
OrderMusic in plain B.music is intended to obtain;Third class intention is not found in technical ability store, by skill development person oneself
Exploitation.The description file of the current technical ability to be developed of editor, it is as follows:
A.music.musicSearch
B.music.orderMusic
This section of music of guessMusicClip issues { friend } and guesses name
GuessMusicClip allows { friend } to hear this section to guess name
Wherein, guessMusicClip is the intention of user oneself exploitation.
Further, skill development person can also be customized the skill elements of selection, such as increase or shielding technical ability is first
Saying template in element, in example as above, it is assumed that skill development person is while selecting A.music.orderMusic, according to application
Increase in demand and part saying template is shielded, the editor that file is described to technical ability is as follows:
A.music.musicSearch
B.music.orderMusic
B.music.orderMusic add points this give { friend }
B.music.orderMusic mask start to request a song
This section of music of guessMusicClip issues { friend } and guesses name
GuessMusicClip allows { friend } to hear this section to guess name
Wherein, add is to increase saying template to being intended to B.music.orderMusic, and mask is that shielding is intended to
The saying template of B.music.orderMusic.
As shown in figure 4, be in the embodiment of the present invention skill development platform determine each skill elements using feature vector
Flow chart includes the following steps:
Step 401, skill development platform in advance divides the technical ability in technical ability store according to vertical field, and obtains
The vertical field class label of technical ability.
Specifically, skill development platform can set initial classes first, in accordance with industry to the division in the vertical field of current technical ability
Then distinguishing label supplements the initial category label in conjunction with the skill collection in technical ability store, obtains technical ability store
The vertical field class label of middle technical ability.
Skill development person selects one or more of initial category label label as current technical ability in Develop ability
Vertical field class label;If the label in initial category label is not enough to describe the vertical field classification of current technical ability,
Then skill development person can be with customized label, to supplement the initial category label of technical ability.Such as the skill development of a shared bicycle
Person can select " trip " label in initial category label, while self-defined " shared " label is added to shared bicycle
In technical ability.
Further, skill development platform can also update the initial category label into Mobile state, can be specifically
Timing is updated or is regularly updated.
It should be noted that each technical ability can there are one or multiple vertical field class labels.
Step 402, according to skilled vertical field class label in technical ability store, the attributive character of each technical ability is calculated
Vector.
The attribute feature vector of technical ability includes the semantic understanding portion of vertical field class label feature, technical ability belonging to technical ability
It is mitogenetic at term vector feature, the online number of request of technical ability, the user's evaluation score of technical ability.The concrete meaning of wherein each feature and
Dimension has been described in detail in front, and details are not described herein.
Certainly, the attributive character of technical ability can also increase other feature other than four kinds of currently used features;Such as technical ability
The number of affiliated vertical field class label, the field vector of the affiliated knowledge mapping of term vector of technical ability, the term vector institute of technical ability
Belong to the field number etc. of knowledge mapping.
Step 403, according to the attribute feature vector of each technical ability, in numeracy skills store the use feature of each skill elements to
Amount.
The use feature vector of the skill elements indicates that current skill elements in skill development, recommend corresponding technical ability
When, the case where technical ability uses and current skill elements are not used.
The skill elements using feature vector can use skill elements recommend the attributive character of corresponding technical ability to
Amount is calculated, specific formula for calculation referring to front formula (1).
It should be noted that due to the online number of request of each technical ability in technical ability store, the user's evaluation of technical ability must grade is
Dynamic change, i.e., the update of the maintenance of technical ability, the vertical field class label of technical ability, technical ability are made according to skill development person
Can be constantly updated with the attributive character of the information such as situation, each technical ability, therefore, in technical ability store skilled attributive character to
After amount update, skill development platform also needs to recalculate the use feature vector of each skill elements in technical ability store.
Skill development platform is based on above-mentioned meter after receiving the attributive character of technical ability to be developed of skill development person's upload
The use feature vector of each skill elements in obtained technical ability store, successively in numeracy skills store each skill elements use
The distance between the attributive character of feature vector and the technical ability to be developed, the skill elements that chosen distance is less than given threshold push away
It recommends to skill development person;Or the ascending skill elements for sorting forward setting number of chosen distance recommend skill development
Person.
Developing method for technical ability provided in an embodiment of the present invention using the shared skill elements issued in technical ability store and is shared
Technical ability recommends corresponding skill elements in skill development person's Develop ability from trend skill development person, and skill development person can be from
The middle skill elements for selecting to meet application demand, then carry out skill development, to greatly improve using the skill elements of selection
The efficiency of skill development, reduces the complexity of skill development.Certainly, the technical ability that skill development person can also complete exploitation
It is published to technical ability store, is used for other skill development persons.
Each embodiment in this specification is described in a progressive manner, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Moreover, described above
System embodiment it is only schematical, wherein the module illustrated as separating component may or may not be
It is physically separated, you can be located at a place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of module therein is selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not
In the case of making the creative labor, you can to understand and implement.
The embodiment of the present invention is described in detail above, specific implementation mode used herein carries out the present invention
It illustrates, the explanation of above example is only intended to help to understand the method and device of the present invention;Meanwhile for the one of this field
As technical staff, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, to sum up institute
It states, the content of the present specification should not be construed as limiting the invention.
Claims (16)
1. a kind of skill development system, which is characterized in that including:Skill development platform and technical ability store;Technical ability stores in store
There are shared technical ability and the skill elements, the skill elements to include:It is the intention of technical ability, the saying template being each intended to encompass, each
The semantic slot that saying template includes;
The skill development platform includes:
Preprocessing module, the use feature vector for determining each skill elements in technical ability store, the skill elements include:Skill
The semantic slot that the intention of energy, saying template, each saying template being each intended to encompass include;
Receiving module, the attributive character of the technical ability to be developed for receiving skill development person's upload;
Recommendation process module, for according in technical ability store each skill elements using feature vector and the technical ability to be developed
Attributive character determines skill elements to be recommended;
Push unit, for the skill elements to be recommended to be recommended the skill development person, so that the skill development
Person selects the skill elements Develop ability for meeting application demand.
2. system according to claim 1, which is characterized in that the preprocessing module includes:
Taxon for being divided in advance according to vertical field to the technical ability in technical ability store, and obtains the vertical of technical ability
Field class label;
First computing unit, for according to skilled vertical field class label in technical ability store, calculating the category of each technical ability
Property feature vector;
Second computing unit, for according to the attribute feature vector of each technical ability, the use of each skill elements in numeracy skills store
Feature vector.
3. system according to claim 2, which is characterized in that the attribute feature vector includes:It is vertical belonging to technical ability
Term vector feature, the online number of request of technical ability, the use of technical ability of the semantic understanding part generation of field class label feature, technical ability
Evaluate score in family.
4. system according to claim 2, which is characterized in that
Second computing unit recalculates after being additionally operable in technical ability store skilled attribute feature vector update
The use feature vector of each skill elements in technical ability store.
5. system according to claim 1, which is characterized in that the recommendation process module includes:
Metrics calculation unit, for after the attributive character that the receiving module receives the technical ability to be developed, calculating successively
The distance between the attributive character using feature vector and the technical ability to be developed of each skill elements in technical ability store;
Selecting unit is less than the skill elements of given threshold as skill elements to be recommended for chosen distance;Or selection
Skill elements apart from the ascending forward setting number that sorts are as skill elements to be recommended.
6. system according to any one of claims 1 to 5, which is characterized in that
The receiving module is additionally operable to receive the technical ability that skill development person uploads, and the technical ability is published to the technical ability quotient
City.
7. a kind of developing method for technical ability, which is characterized in that the method includes:
Determine the attributive character of technical ability to be developed;
The attributive character of the technical ability to be developed is uploaded to skill development platform;
The skill elements that skill development platform is recommended are obtained, the skill elements include:The intention of technical ability is each intended to encompass
The semantic slot that saying template, each saying template include;
Selection meets the skill elements of application demand;
Utilize the skill elements Develop ability of selection.
8. the method according to the description of claim 7 is characterized in that the method further includes:
Skill development platform predefines the use feature vector of each skill elements in technical ability store;
Skill development platform is after the attributive character for receiving the technical ability to be developed, and each technical ability is first in numeracy skills store successively
The distance between the attributive character using feature vector and the technical ability to be developed of element;
The skill elements that chosen distance is less than given threshold are recommended;Or the setting that the ascending sequence of chosen distance is forward
The skill elements of number are recommended.
9. according to the method described in claim 8, it is characterized in that, the skill development platform predefines in technical ability store respectively
The use feature vector of skill elements includes:
The skill development platform in advance divides the technical ability in technical ability store according to vertical field, and obtains hanging down for technical ability
Straight field class label;
According to skilled vertical field class label in technical ability store, the attribute feature vector of each technical ability is calculated;
According to the attribute feature vector of each technical ability, the use feature vector of each skill elements in numeracy skills store.
10. according to the method described in claim 9, it is characterized in that, the skill development platform predefines in technical ability store
The use feature vector of each skill elements further includes:
In technical ability store after skilled attribute feature vector update, the skill development platform recalculates technical ability store
In each skill elements use feature vector.
11. according to the method described in claim 9, it is characterized in that, the attribute feature vector includes:It is vertical belonging to technical ability
Term vector feature, the online number of request of technical ability, the use of technical ability of the semantic understanding part generation of field class label feature, technical ability
Evaluate score in family.
12. the method according to the description of claim 7 is characterized in that the description file of skill elements includes the meaning of skill elements
Figure range and saying example;It is described select to meet the skill elements of application demand include:
Meet the skill elements of application demand according to the selection of the description file of the skill elements.
13. the method according to the description of claim 7 is characterized in that described include using the skill elements Develop ability of selection:
The description file for editing technical ability to be developed, the skill elements of selection are added in technical ability to be developed.
14. the method according to the description of claim 7 is characterized in that described include using the skill elements Develop ability of selection:
The skill elements of selection are customized, the skill elements customized;
The description file for editing technical ability to be developed, the skill elements of customization are added in technical ability to be developed.
15. according to claim 7 to 14 any one of them method, which is characterized in that the method further includes:
If the skill elements that skill development platform is recommended do not meet the skill elements of application demand, by browsing technical ability quotient
The description file selection of other skill elements meets the skill elements of application demand in city, or meets application by retrieving selection
The skill elements of demand.
16. according to claim 7 to 14 any one of them method, which is characterized in that the method further includes:
The technical ability that exploitation is completed is published in the technical ability store.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710774596.4A CN108334353B (en) | 2017-08-31 | 2017-08-31 | Skill development system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710774596.4A CN108334353B (en) | 2017-08-31 | 2017-08-31 | Skill development system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108334353A true CN108334353A (en) | 2018-07-27 |
CN108334353B CN108334353B (en) | 2021-04-02 |
Family
ID=62922414
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710774596.4A Active CN108334353B (en) | 2017-08-31 | 2017-08-31 | Skill development system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108334353B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410922A (en) * | 2018-10-09 | 2019-03-01 | 苏州思必驰信息科技有限公司 | Resource preprocess method and system for voice dialogue platform |
CN111124350A (en) * | 2019-12-20 | 2020-05-08 | 科大讯飞股份有限公司 | Skill determination method and related equipment |
CN111209363A (en) * | 2019-12-25 | 2020-05-29 | 华为技术有限公司 | Corpus data processing method, apparatus, server and storage medium |
JP2021009665A (en) * | 2019-06-28 | 2021-01-28 | バイドゥ オンライン ネットワーク テクノロジー (ベイジン) カンパニー リミテッド | Method, apparatus, and device for generating file, and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6353810B1 (en) * | 1999-08-31 | 2002-03-05 | Accenture Llp | System, method and article of manufacture for an emotion detection system improving emotion recognition |
JP2011221891A (en) * | 2010-04-13 | 2011-11-04 | Seiko Epson Corp | Keyword recording device, customer service support device, keyword recording method and program |
CN102880649A (en) * | 2012-08-27 | 2013-01-16 | 北京搜狗信息服务有限公司 | Individualized information processing method and system |
CN103237050A (en) * | 2013-03-22 | 2013-08-07 | 广东电网公司佛山供电局 | Method and system for intelligent voice interaction |
CN103530428A (en) * | 2013-11-04 | 2014-01-22 | 武汉大学 | Same-occupation type recommendation method based on developer practical skill similarity |
US8714982B2 (en) * | 2007-10-15 | 2014-05-06 | Casey Wimsatt | System and method for teaching social skills, social thinking, and social awareness |
CN105845137A (en) * | 2016-03-18 | 2016-08-10 | 中国科学院声学研究所 | Voice communication management system |
CN106021339A (en) * | 2016-05-09 | 2016-10-12 | 中国联合网络通信集团有限公司 | A semantic query method and system for a resource tree |
CN106371840A (en) * | 2016-08-30 | 2017-02-01 | 北京航空航天大学 | Software development method and device based on crowdsourcing |
CN106558309A (en) * | 2015-09-28 | 2017-04-05 | 中国科学院声学研究所 | A kind of spoken dialog strategy-generating method and spoken dialog method |
CN106663001A (en) * | 2016-06-28 | 2017-05-10 | 深圳狗尾草智能科技有限公司 | A single intention-based skill packet concurrent execution management method and system and a robot |
-
2017
- 2017-08-31 CN CN201710774596.4A patent/CN108334353B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6353810B1 (en) * | 1999-08-31 | 2002-03-05 | Accenture Llp | System, method and article of manufacture for an emotion detection system improving emotion recognition |
US8714982B2 (en) * | 2007-10-15 | 2014-05-06 | Casey Wimsatt | System and method for teaching social skills, social thinking, and social awareness |
JP2011221891A (en) * | 2010-04-13 | 2011-11-04 | Seiko Epson Corp | Keyword recording device, customer service support device, keyword recording method and program |
CN102880649A (en) * | 2012-08-27 | 2013-01-16 | 北京搜狗信息服务有限公司 | Individualized information processing method and system |
CN103237050A (en) * | 2013-03-22 | 2013-08-07 | 广东电网公司佛山供电局 | Method and system for intelligent voice interaction |
CN103530428A (en) * | 2013-11-04 | 2014-01-22 | 武汉大学 | Same-occupation type recommendation method based on developer practical skill similarity |
CN106558309A (en) * | 2015-09-28 | 2017-04-05 | 中国科学院声学研究所 | A kind of spoken dialog strategy-generating method and spoken dialog method |
CN105845137A (en) * | 2016-03-18 | 2016-08-10 | 中国科学院声学研究所 | Voice communication management system |
CN106021339A (en) * | 2016-05-09 | 2016-10-12 | 中国联合网络通信集团有限公司 | A semantic query method and system for a resource tree |
CN106663001A (en) * | 2016-06-28 | 2017-05-10 | 深圳狗尾草智能科技有限公司 | A single intention-based skill packet concurrent execution management method and system and a robot |
CN106371840A (en) * | 2016-08-30 | 2017-02-01 | 北京航空航天大学 | Software development method and device based on crowdsourcing |
Non-Patent Citations (3)
Title |
---|
MA JUN ET AL: "The Exploration of the Strategies and Skills of Effective Use of Voice Recognition Software in the Classroom for Deaf Students", 《 2010 SECOND INTERNATIONAL CONFERENCE ON FUTURE NETWORKS》 * |
刘景泰等: "面向智能家居_智慧生活的服务机器人技术与系统", 《集成技术》 * |
李翠曼等: "基于语义框架填充过程的语义相似度计算", 《计算机工程与设计》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410922A (en) * | 2018-10-09 | 2019-03-01 | 苏州思必驰信息科技有限公司 | Resource preprocess method and system for voice dialogue platform |
JP2021009665A (en) * | 2019-06-28 | 2021-01-28 | バイドゥ オンライン ネットワーク テクノロジー (ベイジン) カンパニー リミテッド | Method, apparatus, and device for generating file, and storage medium |
CN111124350A (en) * | 2019-12-20 | 2020-05-08 | 科大讯飞股份有限公司 | Skill determination method and related equipment |
CN111124350B (en) * | 2019-12-20 | 2023-10-27 | 科大讯飞股份有限公司 | Skill determination method and related equipment |
CN111209363A (en) * | 2019-12-25 | 2020-05-29 | 华为技术有限公司 | Corpus data processing method, apparatus, server and storage medium |
CN111209363B (en) * | 2019-12-25 | 2024-02-09 | 华为技术有限公司 | Corpus data processing method, corpus data processing device, server and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108334353B (en) | 2021-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3996346A1 (en) | Message pushing method, storage medium, and server | |
CN104933113B (en) | A kind of expression input method and device based on semantic understanding | |
CN108334353A (en) | Skill development system and method | |
CN102741875B (en) | Content management device, contents management method, content supervisor and integrated circuit | |
CN110377804A (en) | Method for pushing, device, system and the storage medium of training course data | |
CN103327053B (en) | Online Music method for pushing and system | |
CN105528372B (en) | A kind of address search method and equipment | |
CN107515857A (en) | Semantic understanding method and system based on customization technical ability | |
CN108628811A (en) | The matching process and device of address text | |
CN108520470A (en) | Method and apparatus for generating customer attribute information | |
CN109903065A (en) | A kind of method and apparatus of the candidate score value of determining candidate point | |
CN105205559A (en) | Scenery itinerary route planning system based on multi-source heterogeneous crowd-sourced data | |
US20230049839A1 (en) | Question Answering Method for Query Information, and Related Apparatus | |
CN109214674A (en) | Customer service system management method, customer service system and electronic equipment | |
CN102708164A (en) | Method and system for calculating movie expectation | |
CN110162675A (en) | Generation method, device, computer-readable medium and the electronic equipment of answer statement | |
CN105045911A (en) | Label generating method for user to mark and label generating equipment for user to mark | |
CN102664744A (en) | Group-sending recommendation method in network message communication | |
CN107133339A (en) | Circuit query method and apparatus and storage medium, processor | |
CN114792111A (en) | Data acquisition method and device, electronic equipment and storage medium | |
CN112541072B (en) | Supply and demand information recommendation method and system based on knowledge graph | |
CN110457706A (en) | Interest point name preference pattern training method, application method, device and storage medium | |
CN109446324A (en) | Processing method, device, storage medium and the electronic equipment of sample data | |
CN108875032A (en) | Area type determines method and device | |
CN109919805A (en) | Information-pushing method, user equipment, storage medium and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |